Timezone: »

 
Oral
Towards Black-box Iterative Machine Teaching
Weiyang Liu · Bo Dai · Xingguo Li · Zhen Liu · James Rehg · Le Song

Thu Jul 12 08:50 AM -- 09:00 AM (PDT) @ A6

In this paper, we make an important step towards the black-box machine teaching by considering the cross-space machine teaching, where the teacher and the learner use different feature representations and the teacher can not fully observe the learner's model. In such scenario, we study how the teacher is still able to teach the learner to achieve faster convergence rate than the traditional passive learning. We propose an active teacher model that can actively query the learner (i.e., make the learner take exams) for estimating the learner's status and provably guide the learner to achieve faster convergence. The sample complexities for both teaching and query are provided. In the experiments, we compare the proposed active teacher with the omniscient teacher and verify the effectiveness of the active teacher model.

Author Information

Weiyang Liu (Georgia Tech)
Bo Dai (Georgia Institute of Technology)
Xingguo Li (Princeton University)
Zhen Liu (Georgia Tech)
James Rehg (Georgia Tech)
Le Song (Georgia Institute of Technology)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors